Liu Boyang, Tan Pang-Ning, Zhou Jiayu
Department of Computer Science and Engineering, Michigan State University.
Proc AAAI Conf Artif Intell. 2022 Jun 30;36(4):4101-4108. doi: 10.1609/aaai.v36i4.20328. Epub 2022 Jun 28.
Density estimation is a widely used method for unsupervised anomaly detection. However, the presence of anomalies in training data may severely impact the density estimation process, thereby hampering the use of more sophisticated density estimation methods such as those based on deep neural networks. In this work, we propose RobustRealNVP, a robust deep density estimation framework for unsupervised anomaly detection. Our approach differs from existing flow-based models from two perspectives. First, RobustRealNVP discards data points with low estimated densities during optimization to prevent them from corrupting the density estimation process. Furthermore, it imposes Lipschitz regularization to ensure smoothness in the estimated density function. We demonstrate the robustness of our algorithm against anomalies in training data from both theoretical and empirical perspectives. The results show that our algorithm outperforms state-of-the-art unsupervised anomaly detection methods.
密度估计是一种广泛用于无监督异常检测的方法。然而，训练数据中异常的存在可能会严重影响密度估计过程，从而阻碍使用更复杂的密度估计方法，例如基于深度神经网络的方法。在这项工作中，我们提出了RobustRealNVP，一种用于无监督异常检测的鲁棒深度密度估计框架。我们的方法在两个方面与现有的基于流的模型不同。首先，RobustRealNVP在优化过程中丢弃估计密度较低的数据点，以防止它们破坏密度估计过程。此外，它施加了Lipschitz正则化以确保估计密度函数的平滑性。我们从理论和实证两个角度证明了我们算法对训练数据中异常的鲁棒性。结果表明，我们的算法优于现有的无监督异常检测方法。
